Abstract
We explore recently introduced definition modeling technique that provided the tool for evaluation of different distributed vector representations of words through modeling dictionary definitions of words. In this work, we study the problem of word ambiguities in definition modeling and propose a possible solution by employing latent variable modeling and soft attention mechanisms. Our quantitative and qualitative evaluation and analysis of the model shows that taking into account words’ ambiguity and polysemy leads to performance improvement.- Anthology ID:
- P18-2043
- Volume:
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Editors:
- Iryna Gurevych, Yusuke Miyao
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 266–271
- Language:
- URL:
- https://aclanthology.org/P18-2043
- DOI:
- 10.18653/v1/P18-2043
- Cite (ACL):
- Artyom Gadetsky, Ilya Yakubovskiy, and Dmitry Vetrov. 2018. Conditional Generators of Words Definitions. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 266–271, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- Conditional Generators of Words Definitions (Gadetsky et al., ACL 2018)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/P18-2043.pdf
- Code
- agadetsky/pytorch-definitions
- Data
- WikiText-103, WikiText-2